Edge Tts Chinese

Convert Chinese text or files into MP3 audio using Microsoft Edge's neural voices with customizable voice options.

Security Scan

The skill's code and instructions match its stated purpose (converting Chinese text to MP3 via the edge-tts Python library); nothing requests unrelated credentials or elevated privileges, though you should be aware of dependency and privacy implications.

Purpose & Capability

Name, description, SKILL.md, and the Python implementation all align: the script reads text (CLI, file, or stdin), calls edge_tts to synthesize speech, and writes an MP3. It does not request unrelated credentials or access.

Instruction Scope

Runtime instructions and code stay within the stated scope (read text, synthesize, write MP3). However SKILL.md/code do not call out that edge_tts performs network calls to Microsoft TTS endpoints and that plaintext will be sent over the network — a privacy consideration the user should be aware of.

Install Mechanism

There is no install spec and no declared dependency list; the code imports the third‑party package edge_tts but does not instruct how to install it (e.g., pip install edge-tts). Lack of an install recipe is not dangerous by itself, but you should install and review the edge-tts package from a trusted source (PyPI/GitHub).

Credentials

The skill requests no environment variables or credentials and the code does not access unrelated config paths or secrets. The default output path (/tmp/edge_tts_chinese.mp3) and reading an arbitrary input file are expected for this utility.

Persistence & Privilege

The skill does not request always:true, does not modify other skills or system-wide agent settings, and has no persistent installation steps specified. It runs on demand.

Assessment

This skill appears to do what it claims, but before installing/running: (1) ensure the Python dependency edge-tts is installed from a trusted source (pip install edge-tts) and inspect its repository if you care about supply-chain risk; (2) be aware that the text you synthesize is sent over the network to Microsoft TTS endpoints by edge-tts — avoid sending sensitive secrets or private data; (3) when supplying a --file path, don't point it at sensitive system files; (4) the SKILL.md doesn't include an install step, so add the dependency yourself or run in an environment where edge-tts is preinstalled; and (5) consider running the script in an isolated environment if you are cautious about third-party network activity.

Edge TTS 中文转语音

将中文文章转换为语音音频（仅限中文）。

使用方法

方式1：直接输入文本

python3 edge_tts_chinese.py --text "你的中文文章内容"

方式2：从文件读取

python3 edge_tts_chinese.py --file 文章.txt

方式3：交互式输入

python3 edge_tts_chinese.py
# 然后粘贴文章内容，按 Ctrl+D 结束

参数说明

参数	说明	默认值
--text, -t	直接输入文章内容	-
--file, -f	从文件读取文章	-
--voice, -v	语音名称	zh-CN-XiaoxiaoNeural
--output, -o	输出文件路径	/tmp/edge_tts_chinese.mp3

可用语音

语音	说明
zh-CN-XiaoxiaoNeural	中文女声（默认）
zh-CN-YunxiNeural	中文男声
zh-CN-XiaoyiNeural	中文女声（年轻）
zh-CN-YunyangNeural	中文男声（新闻）

使用场景

• 随时需要将中文文章转为语音时使用
• 例如：新闻朗读、故事讲述、通知播报等

技术说明

• 使用 edge-tts（微软Edge浏览器语音合成）
• 支持长文本（5000+字符测试通过）
• 输出格式：MP3